lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20201210194045.457218278@linutronix.de>
Date:   Thu, 10 Dec 2020 20:26:05 +0100
From:   Thomas Gleixner <tglx@...utronix.de>
To:     LKML <linux-kernel@...r.kernel.org>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Marc Zyngier <maz@...nel.org>,
        Boris Ostrovsky <boris.ostrovsky@...cle.com>,
        Juergen Gross <jgross@...e.com>,
        Stefano Stabellini <sstabellini@...nel.org>,
        xen-devel@...ts.xenproject.org,
        "James E.J. Bottomley" <James.Bottomley@...senPartnership.com>,
        Helge Deller <deller@....de>,
        afzal mohammed <afzal.mohd.ma@...il.com>,
        linux-parisc@...r.kernel.org, Russell King <linux@...linux.org.uk>,
        linux-arm-kernel@...ts.infradead.org,
        Mark Rutland <mark.rutland@....com>,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>,
        Christian Borntraeger <borntraeger@...ibm.com>,
        Heiko Carstens <hca@...ux.ibm.com>, linux-s390@...r.kernel.org,
        Jani Nikula <jani.nikula@...ux.intel.com>,
        Joonas Lahtinen <joonas.lahtinen@...ux.intel.com>,
        Rodrigo Vivi <rodrigo.vivi@...el.com>,
        David Airlie <airlied@...ux.ie>,
        Daniel Vetter <daniel@...ll.ch>,
        Pankaj Bharadiya <pankaj.laxminarayan.bharadiya@...el.com>,
        Chris Wilson <chris@...is-wilson.co.uk>,
        Wambui Karuga <wambui.karugax@...il.com>,
        intel-gfx@...ts.freedesktop.org, dri-devel@...ts.freedesktop.org,
        Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>,
        Linus Walleij <linus.walleij@...aro.org>,
        linux-gpio@...r.kernel.org, Lee Jones <lee.jones@...aro.org>,
        Jon Mason <jdmason@...zu.us>,
        Dave Jiang <dave.jiang@...el.com>,
        Allen Hubbe <allenbh@...il.com>, linux-ntb@...glegroups.com,
        Lorenzo Pieralisi <lorenzo.pieralisi@....com>,
        Rob Herring <robh@...nel.org>,
        Bjorn Helgaas <bhelgaas@...gle.com>,
        Michal Simek <michal.simek@...inx.com>,
        linux-pci@...r.kernel.org,
        Karthikeyan Mitran <m.karthikeyan@...iveil.co.in>,
        Hou Zhiqiang <Zhiqiang.Hou@....com>,
        Tariq Toukan <tariqt@...dia.com>,
        "David S. Miller" <davem@...emloft.net>,
        Jakub Kicinski <kuba@...nel.org>, netdev@...r.kernel.org,
        linux-rdma@...r.kernel.org, Saeed Mahameed <saeedm@...dia.com>,
        Leon Romanovsky <leon@...nel.org>
Subject: [patch 29/30] xen/events: Implement irq distribution

Keep track of the assignments of event channels to CPUs and select the
online CPU with the least assigned channels in the affinity mask which is
handed to irq_chip::irq_set_affinity() from the core code.

Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Cc: Boris Ostrovsky <boris.ostrovsky@...cle.com>
Cc: Juergen Gross <jgross@...e.com>
Cc: Stefano Stabellini <sstabellini@...nel.org>
Cc: xen-devel@...ts.xenproject.org
---
 drivers/xen/events/events_base.c |   72 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 64 insertions(+), 8 deletions(-)

--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -96,6 +96,7 @@ struct irq_info {
 	struct list_head eoi_list;
 	short refcnt;
 	u8 spurious_cnt;
+	u8 is_accounted;
 	enum xen_irq_type type; /* type */
 	unsigned irq;
 	evtchn_port_t evtchn;   /* event channel */
@@ -161,6 +162,9 @@ static DEFINE_PER_CPU(int [NR_VIRQS], vi
 /* IRQ <-> IPI mapping */
 static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1};
 
+/* Event channel distribution data */
+static atomic_t channels_on_cpu[NR_CPUS];
+
 static int **evtchn_to_irq;
 #ifdef CONFIG_X86
 static unsigned long *pirq_eoi_map;
@@ -257,6 +261,32 @@ static void set_info_for_irq(unsigned in
 		irq_set_chip_data(irq, info);
 }
 
+/* Per CPU channel accounting */
+static void channels_on_cpu_dec(struct irq_info *info)
+{
+	if (!info->is_accounted)
+		return;
+
+	info->is_accounted = 0;
+
+	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
+		return;
+
+	WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], -1 , 0));
+}
+
+static void channels_on_cpu_inc(struct irq_info *info)
+{
+	if (WARN_ON_ONCE(info->cpu >= nr_cpu_ids))
+		return;
+
+	if (WARN_ON_ONCE(!atomic_add_unless(&channels_on_cpu[info->cpu], 1,
+					    INT_MAX)))
+		return;
+
+	info->is_accounted = 1;
+}
+
 /* Constructors for packed IRQ information. */
 static int xen_irq_info_common_setup(struct irq_info *info,
 				     unsigned irq,
@@ -339,6 +369,7 @@ static void xen_irq_info_cleanup(struct
 {
 	set_evtchn_to_irq(info->evtchn, -1);
 	info->evtchn = 0;
+	channels_on_cpu_dec(info);
 }
 
 /*
@@ -449,7 +480,9 @@ static void bind_evtchn_to_cpu(evtchn_po
 
 	xen_evtchn_port_bind_to_cpu(evtchn, cpu, info->cpu);
 
+	channels_on_cpu_dec(info);
 	info->cpu = cpu;
+	channels_on_cpu_inc(info);
 }
 
 /**
@@ -622,11 +655,6 @@ static void xen_irq_init(unsigned irq)
 {
 	struct irq_info *info;
 
-#ifdef CONFIG_SMP
-	/* By default all event channels notify CPU#0. */
-	cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(0));
-#endif
-
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (info == NULL)
 		panic("Unable to allocate metadata for IRQ%d\n", irq);
@@ -1691,10 +1719,34 @@ static int xen_rebind_evtchn_to_cpu(evtc
 	return 0;
 }
 
+/*
+ * Find the CPU within @dest mask which has the least number of channels
+ * assigned. This is not precise as the per cpu counts can be modified
+ * concurrently.
+ */
+static unsigned int select_target_cpu(const struct cpumask *dest)
+{
+	unsigned int cpu, best_cpu = UINT_MAX, minch = UINT_MAX;
+
+	for_each_cpu_and(cpu, dest, cpu_online_mask) {
+		unsigned int curch = atomic_read(&channels_on_cpu[cpu]);
+
+		if (curch < minch) {
+			minch = curch;
+			best_cpu = cpu;
+		}
+	}
+
+	/* If this happens accounting is screwed up */
+	if (WARN_ON_ONCE(best_cpu == UINT_MAX))
+		best_cpu = cpumask_first(dest);
+	return best_cpu;
+}
+
 static int set_affinity_irq(struct irq_data *data, const struct cpumask *dest,
 			    bool force)
 {
-	unsigned tcpu = cpumask_first_and(dest, cpu_online_mask);
+	unsigned int tcpu = select_target_cpu(dest);
 	int ret;
 
 	ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
@@ -1922,8 +1974,12 @@ void xen_irq_resume(void)
 	xen_evtchn_resume();
 
 	/* No IRQ <-> event-channel mappings. */
-	list_for_each_entry(info, &xen_irq_list_head, list)
-		info->evtchn = 0; /* zap event-channel binding */
+	list_for_each_entry(info, &xen_irq_list_head, list) {
+		/* Zap event-channel binding */
+		info->evtchn = 0;
+		/* Adjust accounting */
+		channels_on_cpu_dec(info);
+	}
 
 	clear_evtchn_to_irq_all();
 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ